© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54592
    Prev
    Next
    INDEX
    Explanations

    nor or neither

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç©´
    -0.09
    æģģ
    -0.09
    çĭİ
    -0.09
    èįļ
    -0.08
    æĭ±
    -0.08
    åijĽ
    -0.08
    沪
    -0.08
    alo
    -0.08
    alt
    -0.08
    她说
    -0.08
    POSITIVE LOGITS
    åľ¨æł¡
    0.11
    heroes
    0.09
     tamp
    0.09
    å¯Ħ
    0.09
    è°¨
    0.09
    еÑĨ
    0.08
    æĮ¯åħ´
    0.08
     fullPath
    0.08
    ancer
    0.08
    getRepository
    0.08
    Activations Density 0.011%

    No Known Activations